利用Python进行数据分析--USDA食品数据库分析

对USDA食品数据库进行分析，data请见GitHub。
以下主要分为：1.导入数据并检查数据结构；2.整理info表格；3.整理nutrients表格；4.合并两表进行分析。

#导入数据

# 导入数据
import json
db = json.load(open(r'data\usda_food\database.json'))

# 检查数据
db[0].keys()
# dict_keys(['id', 'description', 'tags', 'manufacturer', 'group', 'portions', 'nutrients'])

# 检查数据
db[0]
{
    
    'id': 1008,
 'description': 'Cheese, caraway',
 'tags': [],
 'manufacturer': '',
 'group': 'Dairy and Egg Products',
 'portions': [{
    
    'amount': 1, 'unit': 'oz', 'grams': 28.35}],
 'nutrients': [{
    
    'value': 25.18,
   'units': 'g',
   'description': 'Protein',
   'group': 'Composition'},.....

#整合info表

# 抽取一部分信息，建立info
sub=['id','description','manufacturer','group']
info = DataFrame(db,columns=sub)
info.info()
 #   Column        Non-Null Count  Dtype 
#---  ------        --------------  ----- 
# 0   id            6636 non-null   int64 
# 1   description   6636 non-null   object
# 2   manufacturer  5195 non-null   object
# 3   group         6636 non-null   object

# 通过value_counts 查看食物类别的分布情况
info.group.value_counts()[:5]
#Vegetables and Vegetable Products    812
#Beef Products                        618
#Baked Products                       496
#Breakfast Cereals                    403
#Fast Foods                           365

#整合nutrients表

# 将所有食物的营养成分整合到一张大表中nutrients
nutrients = []
for rec in db:
    frame = DataFrame(rec['nutrients'])
    frame['id'] = rec['id']
    nutrients.append(frame)
nutrients = pd.concat(nutrients)

nutrients

# 丢弃重复项
nutrients.duplicated().sum()
nutrients = nutrients.drop_duplicates()

#对全部营养数据做分析

# 重命名1
col_mapping = {
    
    'description':'food','group':'fgroup'}
info = info.rename(columns=col_mapping,copy=True)
# 重命名2
col_mapping = {
    
    'description':'nutrient','group':'nutgroup'}
nutrients = nutrients.rename(columns=col_mapping,copy=True)
# 将info跟nutrients两个表格合并
ndata = pd.merge(info,nutrients,on='id',how='outer')
ndata[:5]

# 根据营养类型和食物分类画出中位值图
result = ndata.groupby(['nutrient','fgroup'])['value'].quantile(0.5)
result
#nutrient          fgroup                           
#Adjusted Protein  Sweets                               #12.900
#                  Vegetables and Vegetable Products     2.180
#Alanine           Baby Foods                            0.085
#                  Baked Products                        0.248
#                  Beef Products                         1.550
#                                                        #...  
#Zinc, Zn          Snacks                                1.470
#                  Soups, Sauces, and Gravies           0.200
#                  Spices and Herbs                      2.750
#                  Sweets                                0.360
#                  Vegetables and Vegetable Products     0.330
#Name: value, Length: 2246, dtype: float64

# 画出锌的中位值
result['Zinc, Zn'].sort_values().plot(kind='barh')
plt.savefig('Zinc, Zn.jpg',bbox_inches='tight')

# 找出各类最丰富的的食物
get_max = lambda x:x.xs(x.value.idxmax())
max_food = ndata.groupby(['nutgroup','nutrient']).apply(get_max)
max_food = max_food[['food','value']]
max_food